Search

Short-term spatio-temporal solar irradiance forecasting plays a pivotal role in scheduling and dispatching energy for distributed energy systems. Fluctuations in cloud cover can be monitored via satellite cloud imagery, which directly impacts irradiance. However, integrating and fusing multi-source heterogeneous data, such as satellite cloud images and ground monitoring data from distributed stations, remains challenging. Here, a spatio-temporal irradiance forecast model is proposed based on multi-modal deep learning model to predict global horizontal irradiance 30 min ahead. To address the feature extraction of heterogeneous data, a dual-channel structure consisting of a time-series processing block and a satellite cloud image processing block is developed to enable parallel processing of multi-modal features. In order To tightly couple cloud images and historical time series at the feature level, maximum mean discrepancy of these two feature is used to help the fusion of heterogeneous data. Furthermore, a self-attention mechanism is employed to construct adaptive inter-region information weights to enhance spatio-temporal representation ability. The evaluation of the method is conducted on open-access datasets from six locations in Jiangsu Province, China. Experimental results demonstrate that the proposed model efficiently utilizes heterogeneous data to improve prediction accuracy under various conditions and enhances model robustness, reducing RMSE by 2.8%–20.58%. Meanwhile, the proposed end-to-end model reduces training and deployment costs for real-world use. [ABSTRACT FROM AUTHOR]

Automated real time quality monitoring is one of the key enablers for future high-speed production. In this research, an in-process monitoring procedure based on computer vision inspection and deep learning is proposed to indicate the tool and part quality during soft tooling injection moulding. Multiple types of injection moulding defects can be detected by the proposed method. Geometrical dimensions of the part can be measured simultaneously and the uncertainty can be quantified. Based on the obtained data, automated quality evaluation can be achieved in-process and a decision signal can be sent back to the injection moulding system for process adjustment. [ABSTRACT FROM AUTHOR]

With the vigorous development of renewable energy, the installed capacity of photovoltaic (PV) power plants continuously expands. For distributed PV systems, spatio-temporal short-term solar irradiance forecasting can give forecasts for multiple sites simultaneously and help improve the generation of the PV power. However, it is difficult to explore appropriate spatio-temporal relationship for high-dimensional and long-historical data. Thus, an Attention Graph Convolution Long short term memory neural network with Tensor Regression (AGCL-TR) is proposed. Firstly, the adaptive adjacent matrices, which represents the relationship among PV sites, are obtained directly from the encoded feature of the history meteorological data of multiple PV sites by self-attention mechanism. Secondly, graph feature along with original data are handled by AGCL to obtain spatio-temporal feature. Thirdly, a TR network is used to decode the higher-order spatio-temporal feature into next step irradiance forecasts for each PV site. The proposed method is validated on an open access dataset, the National Solar Radiation Database (NSRDB), with eight sites randomly selected in Nevada, North America. The experiment demonstrates that the proposed method outperforms the existing spatio-temporal prediction methods in each site, with an improvement of RMSE of 11.9%–19.8%. The proposed method can effectively extract and preserve the spatio-temporal features of high-dimensional data, which can improve the prediction performance in distributed PV systems. [Display omitted] • A novel model for short-term spatio-temporal irradiance forecast is proposed • Self-attention-based adjacent matrix is introduced to represent spatial interaction. • Graph feature is extracted to enrich spatial feature representation. • Spatio-temporal feature is preserved from compressing by tensor regression network. [ABSTRACT FROM AUTHOR]

β-Cyclodextrin can form inclusion complex with a series of guest molecules including phenyl moieties, and has gained considerable popularity in the study of supramolecular nanostructure. In this study, a biodegradable nanocomplex (HA(CD)-4Phe4 nanocomplex) was developed from β-cyclodextrin grafted hyaluronic acid (HA) and phenylalanine based poly(ester amide). The phenylalanine based poly(ester amide) is a biodegradable pseudo protein which provides the encapsulation capacity for gambogic acid (GA), a naturally-derived chemotherapeutic which has been effectively employed to treat multidrug resistant tumor. The therapeutic potency of free GA is limited due to its poor solubility in water and the lack of tumor-selective toxicity. The nanocomplex carrier enhanced the solubility and availability of GA in aqueous media, and the HA component enabled the targeted delivery to tumor cells with overexpression of CD44 receptors. In the presence of hyaluronidase, the release of GA from the nanocomplex was significantly accelerated, due to the enzymatic biodegradation of the carrier. Compared to free GA, GA-loaded nanocomplex exhibited improved cytotoxicity in MDA-MB-435/MDR multidrug resistant melanoma cells, and induced enhanced level of apoptosis and mitochondrial depolarization, at low concentration of GA (1–2 µM). The nanocomplex enhanced the therapeutic potency of GA, especially when diluted in physiological environment. In addition, suppressed matrix metalloproteinase activity was also detected in MDA-MB-435/MDR cells treated by GA-loaded nanocomplex, which demonstrated its potency in the inhibition of tumor metastasis. The in vitro data suggested that HA(CD)-4Phe4 nanocomplex could provide a promising alternative in the treatment of multidrug resistant tumor cells. Statement of Significance Gambogic acid (GA), naturally derived from genus Garcinia trees, exhibited significant cytotoxic activity against multiple types of tumors with resistance to traditional chemotherapeutics. Unfortunately, the poor solubility of GA in conventional pharmaceutical solvents and non-targeted distribution in normal tissues greatly limited its therapeutic potency. To overcome the challenges, we develop a nanoplatform from the supramolecular assembly of β-cyclodextrin grafted hyaluronic acid (HA) and phenylalanine based pseudo protein. The pseudo protein in the nanocomplex provided the hydrophobic interaction and loading capacity for GA, while the HA component targeted the overexpressed CD44 receptor and improved the selective endocytosis in multidrug resistant melanoma cells. The supramolecular nanocomplex provide a promising platform for the delivery of hydrophobic chemotherapeutics to improve the bioavailability and efficiency. [ABSTRACT FROM AUTHOR]

Accurate intra-hour irradiance forecasting plays an important role in improving the effectiveness of photovoltaic power management. More and more sensors, for example, total sky imager and cloud sensors, are widely used in photovoltaic plants, so that various factors could be comprehensively concerned to improve the accuracy of forecast. However, the existing methods have difficulty in encoding heterogeneous multi-source data dynamically. To mitigate these problems and improve the practicality of the model, an ensemble learning based multi-modal intra-hour irradiance forecasting method is proposed to forecast the global horizontal solar irradiance in the next 10 min. First, six base learners are built by selecting different combinations of multi-modal data as inputs for considering various factors. Then, a linear ridge regressor is used to integrate the pre-trained base learners to obtain outputs. Furthermore, to improve the robustness of the ensemble models, a dynamical fine-tuning scheme based on clear sky index is proposed. The weather states are predicted by a hidden Markov model based on the clear sky index. Experiments show that the proposed forecasting method effectively improves the accuracy of intra-hour irradiance forecasting by 11.6% when compared with commonly used models. [Display omitted] • Multi-modal data features are effectively incorporated through ensemble learning. • The applicability for data with different sampling rates makes the method practical. • Meta-learner parameters are fine-tuned using clear sky index for the robustness. • Valid information is captured by different base learners to mitigate overfitting. [ABSTRACT FROM AUTHOR]

• Innovative efficiency: Introducing a novel absolute phase extraction algorithm requiring only three grayscale images for high-speed 3D reconstruction. • Robust performance: Demonstrating resilience to environmental factors such as noise, reflectivity variations, and shadows commonly encountered in practical measurement scenarios. • Adaptive error correction: Proposing an error correction technique that adaptively self-corrects non-linear errors in the phase obtained through the algorithm, ensuring enhanced accuracy. • Cost-effective solution: Eliminating the need for additional pattern-assisted phase unwrapping or expensive equipment, providing a cost-effective 3D measurement solution. • Dynamic scene advantage: Outperforming in dynamic scenes, achieving high-quality reconstruction with minimal projected fringes and reduced computational requirements. The structured light three-dimensional (3D) measurement technology based on optical metrics has gained increasing applications, and there is a growing demand for capturing transient trajectory changes in dynamic scenes. Conventional temporal phase unwrapping (TPU) approaches often require multi-frequency fringe patterns for application. However, the inevitable conflict arises between the number of projected fringe patterns and the measurement speed. This paper proposes a highly accurate and robust 3D measurement method using only 3-step phase-shifting fringe patterns. To precisely reconstruct the 3D shape using the fewest fringe patterns, it is essential to extract as much information as possible from the available patterns. Therefore, we calculate the wrapped phase distribution using 3-step phase-shifting fringe patterns to ensure accuracy. Simultaneously, the trapezoidal phase-shifting method is employed to calculate the intensity ratio distribution. Through the proposed region-based indexing method, the intensity ratio map is transformed into an unwrapped phase map. Additionally, a novel self-correction method is introduced to correct the non-linear errors in the unwrapped phase map, which is then utilized for the calculation of the fringe order required for phase unwrapping. This high-speed measurement method utilizes only 3-step phase-shifting fringe patterns while retaining the advantages of TPU, meeting the requirements of high-speed and full-field measurements. Experimental results on both static and dynamic scenes validate the effectiveness and versatility of the proposed method, demonstrating its flexibility and simplicity in application. In our 3D measurement system, the method achieves 3D reconstruction of the dynamic object's trajectory at a measurement speed of 107 frames per second. [ABSTRACT FROM AUTHOR]

• A novel and effective simulation dataset generation method for FPP is proposed. • Neural network trained with simulated datasets is employed to achieve dual-frequency phase unwrapping in actual scenarios with accuracy comparable to the triple-frequency hierarchical phase unwrapping. • Perform dual-frequency phase unwrapping based on the principle of regression and segmentation respectively, an explanation for the difference in performance is give. • Neural network driven by the simulation dataset exhibits high robustness under different degrees of noise contamination. • The importance of the shape and position distribution of the phases in the simulation dataset for neural network to perform phase unwrapping is demonstrated. In fringe projection profilometry (FPP), hierarchical temporal phase unwrapping is used to reliably eliminate phase ambiguity in complex scenarios, in which triple-frequency hierarchical temporal phase unwrapping (THPU) has excellent accuracy but lower measurement speed, while dual-frequency hierarchical temporal phase unwrapping (DHPU) requires only two wrapped phases, but it is fragile to noise contamination. Some researchers have shown that deep learning techniques can be used to overcome this dilemma, but the high dataset building cost makes it difficult to apply them rapidly. In this paper, a novel simulation dataset generation method for FPP is proposed, which requires only a set of pre-collected fringe sequences on the reference plane along with some historical masks to generate a dataset, which is then used to train a neural network. The appropriately trained neural network is able to perform dual-frequency phase unwrapping in actual scenarios based on the principle of regression and segmentation respectively, and both of them show accuracy comparable to THPU, but segmentation is slightly better than regression. We verify its effectiveness through comparative experiments and demonstrate its robustness with different degrees of noise contamination. We believe that this paper can provide potential and beneficial ideas for simulation dataset driven deep learning techniques for optimizing various processes in the field of optical measurements. [ABSTRACT FROM AUTHOR]

Accurate solar irradiance forecasts can make solar power forecasts more reliable, which can help the power grid dispatch reasonably. In practice, Numerical Weather Prediction (NWP) is widely applied in solar irradiance forecasts. In this paper, the statistical NWP Global Horizontal Irradiance (GHI) error analysis shows that the characteristics of NWP GHI error vary obviously under different weather conditions. However, existing correction methods are not designed contrapuntally for different weather conditions, resulting in poor correction performance. To solve this problem, a hybrid method is proposed to get day-ahead correction results for NWP GHI. Specifically, the hybrid method consists of three key parts, including Deep Clustering (DC), Variational Mode Decomposition (VMD), and an Encoder–Decoder based Correction model (EDC). DC is used to categorize the historical samples into three clusters, the input of which is the multi-dimensional information series containing observed data and NWP data. After a feature selection by VMD, the correction models are trained on each cluster respectively. The performance of the proposed model is evaluated with a public dataset and an actual field dataset, and the results demonstrate that the accuracy has been effectively improved by the proposed method compared with other models. In addition, we find that adopting VMD is effective in improving the correction accuracy, and the root mean square error is reduced by 5.70% and 9.32% compared with models without it. • Propose a novel hybrid model for day-ahead NWP solar irradiance correction. • NWP GHI error analysis shows it varies obviously under different weather conditions. • Jointly optimize the feature learning and clustering assignment by DC. • CLSTM is applied to learn effective features of multi-dimensional input data. • Remove redundant information of solar irradiance by VMD to reduce correction error. [Display omitted] [ABSTRACT FROM AUTHOR]

In optical measurement techniques, when the projector works at a constant projection rate, reducing the number of projected fringe patterns is an effective way to reduce the projection time. In this paper, we propose a few-fringe-based phase-shifting profilometry employing Hilbert transform. We project only two fringe patterns for each frequency of fringes, with the phase shift between the fringes designed to be π. The Hilbert transform makes these two captured fringes phase shifted by π /2, thus transforming the original two fringes into four, and the wrapped phase can be obtained through these four fringes with a phase difference of π /2. To improve the accuracy and robustness of the method, we adopt three frequencies of fringes for phase unwrapping. Further, since different phase unwrapping methods can be used for the different frequencies of the fringes, we propose a heterodyne 2H+2 M+2 L method and a hierarchical 2H+2 M+2 L respectively. Multiple experimental results have confirmed the feasibility and effectiveness of the two 2H+2 M+2 L methods, and the different characteristics of the reconstructed shapes obtained by the two 2H+2 M+2 L methods are compared to provide useful guidance in the selection of the required method for different application scenarios. The experimental results demonstrate that when using the heterodyne and hierarchical methods for phase unwrapping, the RMSE of the 2H+2 M+2 L method is only higher than that of the three-frequency four-step phase-shifting method by 0.0056 and 0.0024 respectively, but this 2H+2 M+2 L method improves the efficiency of the three-frequency four-step phase-shifting method by 50%. • Our proposed method requires only two fringes to calculate the wrapped phase for each frequency fringe. • We analyzed the phase error of our proposed two-fringe method and found it comparable to the wrapped phase error of the 4-step phase-shifting method. • We experimentally analyzed the transformation results of fringes with different frequencies using the Hilbert transform. • We provide the fringe generation and wrapped phase calculation formulas for the commonly used heterodyne and hierarchical methods in temporal phase unwrapping. [ABSTRACT FROM AUTHOR]

Bio-MOF-1 is a kind of metal-organic frameworks (MOFs) with bio-derived constitution, self-fabricated by zinc-adeninate secondary building units (SBUs) and may theoretically be endowed with biocompatible behaviors. Its biological applications currently contain several small molecule drugs delivery and in vitro mineralization, yet the related evidence on its biosafety and biocompatibility is still in great need. With the aid of self-modified protocol to synthesize micro/nanoscale bio-MOF-1 (m/n-bio-MOF-1), this study aimed to implement a systematic evaluation based on a series of tests from different dimensions including cell proliferation, oxidative stress, apoptosis and animal experiment, etc. These in vitro & in vivo biosafety and biocompatibility tests are to provide fresh evidence and advice for further applications. The outcomes indicated a concentration-dependent trend that 50 and 20 μg/mL groups proved biofriendly, with n-bio-MOF-1 surpassing m-bio-MOF-1. In conclusion, this work provided systematic evidence for the biosafety of m/n-bio-MOF-1, paved the way for their further exploration, and appealed more emphasis on MOFs toxicity. [Display omitted] • The first-time report on the synthesis of nano bio-MOF-1. • The synthesis protocol was modified individually without identical one reported. • The first systematic evaluation on the biosafety between micro & nano bio-MOF-1. • Nano bio-MOF-1 at low concentration indicated less toxicity. • Emphasis on the priority of biosafety assessment on MOFs before bio applications. [ABSTRACT FROM AUTHOR]